arXiv subjects

Thorin Farnsworth

Publications and source records attributed to Thorin Farnsworth.

4 recordsLinked to original sources

arXiv2025

A Binary Optimisation Algorithm for Near-Term Photonic Quantum Processors

Binary optimisation tasks are ubiquitous in areas ranging from logistics to cryptography. The exponential complexity of such problems means that the performance of traditional computational methods decreases rapidly with increasing problem sizes. Here, we propose a new algorithm for binary optimisation, the Bosonic Binary Solver, designed for near-term photonic quantum processors. This variational algorithm uses samples from a quantum optical circuit, which are post-processed using trainable classical bit-flip probabilities, to propose candidate solutions. A gradient-based training loop finds progressively better solutions until convergence. We perform ablation tests that validate the structure of the algorithm. We then evaluate its performance on an illustrative range of binary optimisation problems, using both simulators and real hardware, and perform comparisons to classical algorithms. We find that this algorithm produces high-quality solutions to these problems. As such, this algorithm is a promising method for leveraging the scalable nature of photonic quantum processors to solve large-scale real-world optimisation problems.

quant-ph↗

arXiv2025

Quantum latent distributions in deep generative models

Many successful families of generative models leverage a low-dimensional latent distribution that is mapped to a data distribution. Though simple latent distributions are often used, the choice of distribution has a strong impact on model performance. Recent experiments have suggested that the probability distributions produced by quantum processors, which are typically highly correlated and classically intractable, can lead to improved performance on some datasets. However, when and why latent distributions produced by quantum processors can improve performance, and whether these improvements are connected to quantum properties of these distributions, are open questions that we investigate in this work. We show in theory that, under certain conditions, these "quantum latent distributions" enable generative models to produce data distributions that classical latent distributions cannot efficiently produce. We provide intuition as to the underlying mechanisms that could explain a performance advantage on real datasets. Based on this, we perform extensive benchmarking on a synthetic quantum dataset and the QM9 molecular dataset, using both simulated and real photonic quantum processors. We find that the statistics arising from quantum interference lead to improved generative performance compared to classical baselines, suggesting that quantum processors can play a role in expanding the capabilities of deep generative models.

cs.LG↗

arXiv2022

BESS: Balanced Entity Sampling and Sharing for Large-Scale Knowledge Graph Completion

We present the award-winning submission to the WikiKG90Mv2 track of OGB-LSC@NeurIPS 2022. The task is link-prediction on the large-scale knowledge graph WikiKG90Mv2, consisting of 90M+ nodes and 600M+ edges. Our solution uses a diverse ensemble of $85$ Knowledge Graph Embedding models combining five different scoring functions (TransE, TransH, RotatE, DistMult, ComplEx) and two different loss functions (log-sigmoid, sampled softmax cross-entropy). Each individual model is trained in parallel on a Graphcore Bow Pod$_{16}$ using BESS (Balanced Entity Sampling and Sharing), a new distribution framework for KGE training and inference based on balanced collective communications between workers. Our final model achieves a validation MRR of 0.2922 and a test-challenge MRR of 0.2562, winning the first place in the competition. The code is publicly available at: https://github.com/graphcore/distributed-kge-poplar/tree/2022-ogb-submission.

cs.LG↗

arXiv2022

WakeUpNet: A Mobile-Transformer based Framework for End-to-End Streaming Voice Trigger

End-to-end models have gradually become the main technical stream for voice trigger, aiming to achieve an utmost prediction accuracy but with a small footprint. In present paper, we propose an end-to-end voice trigger framework, namely WakeupNet, which is basically structured on a Transformer encoder. The purpose of this framework is to explore the context-capturing capability of Transformer, as sequential information is vital for wakeup-word detection. However, the conventional Transformer encoder is too large to fit our task. To address this issue, we introduce different model compression approaches to shrink the vanilla one into a tiny one, called mobile-Transformer. To evaluate the performance of mobile-Transformer, we conduct extensive experiments on a large public-available dataset HiMia. The obtained results indicate that introduced mobile-Transformer significantly outperforms other frequently used models for voice trigger in both clean and noisy scenarios.

cs.SD↗